© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 28077
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis followed by code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    redo
    -0.09
     traveler
    -0.08
     cel
    -0.08
    beg
    -0.08
     Undert
    -0.08
    -meta
    -0.08
     Rico
    -0.08
    Ñĥж
    -0.08
     [âĢ¦]
    -0.07
     handing
    -0.07
    POSITIVE LOGITS
     lead
    0.14
     Lead
    0.14
     Leads
    0.13
     follow
    0.13
     lets
    0.13
    Lead
    0.13
     hurry
    0.13
     nearby
    0.13
     led
    0.12
     Lets
    0.12
    Activations Density 0.019%

    No Known Activations